Research on the Bus Passenger Motion Vector Algorithm Based on Video Image

You are here: Homepage > Search

Research on the Bus Passenger Motion Vector Algorithm Based on Video Image

Xiang, Huai Kun / Cheng, Lan Qiu

Video-based bus passenger collection is considered to have a greater potential for counting passengers, but the difficulty lies in how to solve the problem of accurately tracking and determining the direction of the moving target under the complex state of motion. The traditional target detection algorithm, like frame subtraction and edge detection, is very difficult to deal with the situation of immediate multi-objective. Based on image preprocessing, an algorithm about intelligent video multi-target tracking and traffic statistics is designed aiming at the above-mentioned situation. The core contents in this paper includes: the grid-density clustering and line segment clustering, extraction and segmentation target connected domain that is handled to be a circular, tracking the motion vector of target feature point, finally ,achieving accurate statistics on the number of people getting on and off. Experiments show that this algorithm can effectively track more people simultaneously and the bus traffic statistical accuracy achieves the goal.